Title :
Dependability Modeling and Analysis for the Virtual Data Center of Cloud Computing
Author :
Wei, Bing ; Lin, Chuang ; Kong, Xiangzhen
Author_Institution :
Dept. of Comput. Sci. & Technol., Tsinghua Univ., Beijing, China
Abstract :
Virtual data center is becoming increasingly popular as the infrastructure of Cloud computing. In order to provide efficient and uninterrupted service, the dependability of the Cloud infrastructure has received extensive attention. But modeling and analysis of dependability of the virtual data center is challenging for the particular characteristics and mechanisms of virtualization. In this paper, we use hierarchical method and develop the hybrid models combining reliability block diagrams and general stochastic Petri nets. Focusing on the two attributes reliability and availability, we give the computation expressions by solving the models. The impact of the characteristics and mechanisms of virtualization such as consolidation backup and live migration on dependability is studied. We analyze the relation between reliability and consolidation ratio, as well as the relation between availability and the workload. In addition, some useful rules are summarized and discussed, which are believed to be helpful to the design and construction of more dependable virtual data center.
Keywords :
Petri nets; cloud computing; computer centres; data handling; reliability; stochastic processes; virtual reality; cloud computing; cloud infrastructure; consolidation backup; dependability analysis; dependability modeling; hierarchical method; hybrid model; reliability block diagram; reliability consolidation ratio; stochastic Petri nets; uninterrupted service; virtual data center; Analytical models; Availability; Computational modeling; Maintenance engineering; Servers; Virtual machining; Cloud Computing; Dependability; general stochastic Petri net; reliability block diagram; virtual data centers;
Conference_Titel :
High Performance Computing and Communications (HPCC), 2011 IEEE 13th International Conference on
Conference_Location :
Banff, AB
Print_ISBN :
978-1-4577-1564-8
Electronic_ISBN :
978-0-7695-4538-7
DOI :
10.1109/HPCC.2011.111